Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3667 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4438. Min Range: -2.4438

Max Act: 2.3879. Min Act: -0.0000

Data Index: 379697 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 2.4438. Min Range: -2.4438

Max Act: 2.1569. Min Act: -0.0000

Data Index: 693046 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 2.4438. Min Range: -2.4438

Max Act: 2.4438. Min Act: -0.0000

Data Index: 1269787 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 2.4438. Min Range: -2.4438

Max Act: 2.1358. Min Act: -0.0000

Data Index: 1220814 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 2.4438. Min Range: -2.4438

Max Act: 2.0952. Min Act: -0.0000

Data Index: 784434 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.9690. Min Act: -0.0000

Data Index: 26852 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.9119. Min Act: -0.0000

Data Index: 1200172 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.9242. Min Act: -0.0000

Data Index: 805823 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.7630. Min Act: -0.0000

Data Index: 1308070 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.6440. Min Act: -0.0000

Data Index: 537972 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.8076. Min Act: -0.0000

Data Index: 254438 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.6821. Min Act: -0.0000

Data Index: 178637 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 2.4438. Min Range: -2.4438

Max Act: 2.0223. Min Act: -0.0000

Data Index: 739413 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.7708. Min Act: -0.0000

Data Index: 1000935 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.6702. Min Act: -0.0000

Data Index: 795931 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.8843. Min Act: -0.0000

Data Index: 591591 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.6496. Min Act: -0.0000

Data Index: 635862 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.8117. Min Act: -0.0000

Data Index: 1204673 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.6024. Min Act: -0.0000

Data Index: 1037856 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 2.4438. Min Range: -2.4438

Max Act: 1.7068. Min Act: -0.0000

Data Index: 949735 (C4 (Web Text))

Max Activating Token Index: 570